Salah Ghamizi

6 papers · 2022–2024 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) ❓ The Questioner

Venues

NeurIPS (2) AAAI (1) ACL (1) ICML (1) IJCAI (1)

Top co-authors

Maxime Cordy (6) Yves Le Traon (3) Thibault Simonetto (3) Mike Papadakis (2) Salijona Dyrmishi (2) Jingfeng ZHANG (1) Masashi Sugiyama (1)

Research topics

Machine Learning (6) Learning Types · Machine Learning (6) Deep Learning (5) Learning Types · Deep Learning (5) Application Areas (4) Artificial Intelligence (3) Core AI (3) Architectures (2) Core Methods (2) Optimization & Theory (2) Natural Language Processing (1) Applications (1) Techniques (1)

Keywords

adversarial robustness (5) adversarial attack (4) deep neural network (2) multi-task learning (2) auxiliary task (2) evasion attack (2) gradient attack (2) model robustness (2) machine learning (1) adversarial defense (1) tabular data (1) adversarial example (1) tabular deep learning (1) classification model (1) robustification mechanism (1) robust accuracy (1) human evaluation (1) adversarial retraining (1) text perturbation (1) task augmentation (1)

Papers

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data NeurIPS 2024 TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases NeurIPS 2024 GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks ICML 2023 How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks ACL 2023 Adversarial Robustness in Multi-Task Learning: Promises and Illusions AAAI 2022 A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space IJCAI 2022